基于支撑向量机概率输出的高光谱影像混合像元分解

基金项目: 国家自然科学基金资助项目(40471088);国家973计划资助项目(2003CB415205)

详细信息

Unmixing of Hyperspectral Imagery Based on Probabilistic Outputs of Support Vector Machines

¹ State Key Laboratory for Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,129 Luoyu Road,Wuhan 430079,China

Funds: 国家自然科学基金资助项目(40471088);国家973计划资助项目(2003CB415205)

摘要: 提出利用支撑向量机(SVM)后验概率来分解高光谱影像的混合像元,通过支撑向量机的输出值转化为两两配对的后验概率,再由两两配对的概率值求得多类后验概率,并以像元所属类别的后验概率作为地物的组分信息。实验结果表明,该方法能较好地估计出混合像元的组分比。
- 支撑向量机 /
- 多类 /
- 后验概率 /
- 像元分解 /
- 高光谱
Abstract: This paper proposes to estimate abundances from hyperspectral image using probability outputs of support vector machines(SVMs),trains a SVM with a gauss kernel function,and trains the parameters of an additional sigmoid function to map the SVM outputs into probabilities.An experiment of real hyperspectral image is conducted to validate the procedure.The abundances estimated by SVM comparison with those of the linear spectral unmixing are also given.The experiment results show that the method can provide effective result of abundance estimation for hyperspectral image.
- support vector machine(SVM) /
- multi-class /
- posterior probability /
- pixel unmixing /
- hyperspectral imagery